Demosaicking DoFP images using edge compensation method based on correlation

Abstract

With the development of nanotechnology, the division of focal plane (DoFP) infrared polarization imaging system with real-time imaging has matured. Meanwhile, the demand for real-time acquisition of polarization information is growing, but the super-pixel structure of the DoFP polarimeter will bring instantaneous field of view (IFoV) errors. Existing polarization demosaicking methods cannot satisfy both accuracy and speed in terms of efficiency and performance. According to the characteristics of DoFP, this paper proposes an edge compensation demosaicking method by analyzing the channel correlations of polarized images. The method performs demosaicing in the differential domain, and the proposed method's performance is verified by comparison experiments using synthetic and authentic polarized images in the near-infrared (NIR) band. The proposed method outperforms the state-of-the-art methods in terms of accuracy and efficiency. It achieves an average peak signal-to-noise ratio (PSNR) improvement of 2 db on public datasets compared to current state-of-the-art methods. A typical 768 × 1024 specification short-wave infrared (SWIR) polarized image can be processed in 0.293s on the Intel Core i7-10870 H CPU, and the technique significantly outperforms various existing demosaicking methods.